Re: [patch] kstat change to see how much Linux SMP really scale well
Andi Kleen (ak@muc.de)
Sat, 13 Mar 1999 14:05:10 +0100
On Sat, Mar 13, 1999 at 01:13:42PM +0100, Andrea Arcangeli wrote:
> > Now the dream would be detailed per spinlock counters,
> > unfortunately the current spinlock declaration syntax makes it hard
> > to name them (and for dynamic spinlocks embedded in other
> > structures a different way would be needed anyways than to
> > statically name the spinlocks - for them reading System.map doesn't
> > work well neither). This means for named spinlock profiling it is
> > needed to change all spinlock users :(:(. I believe for effective
> > SMP tuning in 2.3 they are definitely needed though.
>
> I think this is something has to be done in the patch-ikd-arca and not in
> the mainstream kernel. patch-ikd-arca has just many neat features very
> very useful for both profiling and debugging the kernel. But since it's
> only something that only hackers will care about it's here instead of in
> the kernel ;)
>
> ftp://e-mind.com/pub/linux/patch-ikd-arca/
>
> I forget to do a 2.2.3 release, hopefully the 2.2.2 will works fine in
> 2.2.3...
I think spin lock profiling is important enough that it should get into 2.3.x.
For 2.2 timeframe existence in -ikd is probably the best way.
-Andi
--
This is like TV. I don't like TV.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/